© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 116685
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "availability"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (er
    -0.08
    oldur
    -0.07
    Mahon
    -0.07
    gnore
    -0.07
    íĭ±
    -0.07
     Kv
    -0.07
    ITTE
    -0.07
    Ral
    -0.07
    нд
    -0.07
    ertz
    -0.07
    POSITIVE LOGITS
    iness
    0.08
    readcr
    0.07
    ailability
    0.07
    ary
    0.07
    ense
    0.06
    wise
    0.06
    inous
    0.06
    ssel
    0.06
    yn
    0.06
    conscious
    0.06
    Activations Density 0.005%

    No Known Activations